Reduce Interobserver Variability Research Articles

Investigation of the Effectiveness of an Algorithm as an Auxiliary Method in Intraoperative Consultations of Central Nervous System Tumors.

One of the most difficult areas in a surgical pathology practice is intraoperative consultation. In a previous study, we proposed an algorithm that provides a systematic approach to intraoperative consultation for central nervous system tumors. Our aim was to demonstrate the effectiveness of this algorithm. 102 cases were selected from intraoperative consultation procedures performed at our institution between 2012 and 2020. The algorithm was tested by five observers. The observers examined the smears and frozen sections without the algorithm, and then with the algorithm. The percentage change in the rate of correct diagnoses made by the four observers (O) increased after using the algorithm (O2: 8%, O3: 5%, O4: 8% and O5: 13%), but decreased for only one observer (O1) (5%). The most common error made by the four observers was `grading of glial tumors` (O1: 40%; O2: 23%; O4: 40% and O5: 27.5%), and this group of errors was mostly corrected by using the algorithm (O1: 33%; O2: 3.8%; O4: 23% and O5: 10%). For two observers (O2 and O5), a statistically significant change in diagnostic levels was observed after using the algorithm (p=0.024 and p=0.040; respectively). In addition, thanks to the use of the algorithm, a high degree of agreement was found between the observers` diagnoses (77.7%, p < 0.001). In the intraoperative consultation of central nervous system lesions, algorithms can help to increase the accuracy of the diagnosis and reduce interobserver variability. This study demonstrates that an algorithmic approach is an effective method for pathologists in intraoperative consultation procedures.

Perspectives on technology: Prostate Imaging-Reporting and Data System (PI-RADS) interobserver variability.

To explore the topic of Prostate Imaging-Reporting and Data System (PI-RADS) interobserver variability, including a discussion of major sources, mitigation approaches, and future directions. A narrative review of PI-RADS interobserver variability. PI-RADS was developed in 2012 to set technical standards for prostate magnetic resonance imaging (MRI), reduce interobserver variability at interpretation, and improve diagnostic accuracy in the MRI-directed diagnostic pathway for detection of clinically significant prostate cancer. While PI-RADS has been validated in selected research cohorts with prostate cancer imaging experts, subsequent prospective studies in routine clinical practice demonstrate wide variability in diagnostic performance. Radiologist and biopsy operator experience are the most important contributing drivers of high-quality care among multiple interrelated factors including variability in MRI hardware and technique, image quality, and population and patient-specific factors such as prostate cancer disease prevalence. Iterative improvements in PI-RADS have helped flatten the curve for novice readers and reduce variability. Innovations in image quality reporting, administrative and organisational workflows, and artificial intelligence hold promise in improving variability even further. Continued research into PI-RADS is needed to facilitate benchmark creation, reader certification, and independent accreditation, which are systems-level interventions needed to uphold and maintain high-quality prostate MRI across entire populations.

Optimizing SUV Analysis: A Multicenter Study on Preclinical FDG-PET/CT Highlights the Impact of Standardization

PurposePreclinical imaging, with translational potential, lacks a standardized method for defining volumes of interest (VOIs), impacting data reproducibility. The aim of this study was to determine the interobserver variability of VOI sizes and standard uptake values (SUVmean and SUVmax) of different organs using the same [18F]FDG-PET and PET/CT datasets analyzed by multiple observers. In addition, the effect of a standardized analysis approach was evaluated.ProceduresIn total, 12 observers (4 beginners and 8 experts) analyzed identical preclinical [18F]FDG-PET-only and PET/CT datasets according to their local default image analysis protocols for multiple organs. Furthermore, a standardized protocol was defined, including detailed information on the respective VOI size and position for multiple organs, and all observers reanalyzed the PET/CT datasets following this protocol.ResultsWithout standardization, significant differences in the SUVmean and SUVmax were found among the observers. Coregistering CT images with PET images improved the comparability to a limited extent. The introduction of a standardized protocol that details the VOI size and position for multiple organs reduced interobserver variability and enhanced comparability.ConclusionsThe protocol offered clear guidelines and was particularly beneficial for beginners, resulting in improved comparability of SUVmean and SUVmax values for various organs. The study suggested that incorporating an additional VOI template could further enhance the comparability of the findings in preclinical imaging analyses.

Use of an Artificial Intelligence-Generated Vascular Severity Score Improved Plus Disease Diagnosis in Retinopathy of Prematurity

To evaluate whether providing clinicians with an artificial intelligence (AI)-based vascular severity score (VSS) improves consistency in the diagnosis of plus disease in retinopathy of prematurity (ROP). Multireader diagnostic accuracy imaging study. Eleven ROP experts, 9 of whom had been in practice for 10 years or more. RetCam (Natus Medical Incorporated) fundus images were obtained from premature infants during routine ROP screening as part of the Imaging and Informatics in ROP study between January 2012 and July 2020. From all available examinations, a subset of 150 eye examinations from 110 infants were selected for grading. An AI-based VSS was assigned to each set of images using the i-ROP DL system (Siloam Vision). The clinicians were asked to diagnose plus disease for each examination and to assign an estimated VSS (range, 1-9) at baseline, and then again 1 month later with AI-based VSS assistance. A reference standard diagnosis (RSD) was assigned to each eye examination from the Imaging and Informatics in ROP study based on 3 masked expert labels and the ophthalmoscopic diagnosis. Mean linearly weighted κ value for plus disease diagnosis compared with RSD. Area under the receiver operating characteristic curve (AUC) and area under the precision-recall curve (AUPR) for labels 1 through 9 compared with RSD for plus disease. Expert agreement improved significantly, from substantial (κ value, 0.69 [0.59, 0.75]) to near perfect (κ value, 0.81 [0.71, 0.86]), when AI-based VSS was integrated. Additionally, a significant improvement in plus disease discrimination was achieved as measured by mean AUC (from 0.94 [95% confidence interval (CI), 0.92-0.96] to 0.98 [95% CI, 0.96-0.99]; difference, 0.04 [95% CI, 0.01-0.06]) and AUPR (from 0.86 [95% CI, 0.81-0.90] to 0.95 [95% CI, 0.91-0.97]; difference, 0.09 [95% CI, 0.03-0.14]). Providing ROP clinicians with an AI-based measurement of vascular severity in ROP was associated with both improved plus disease diagnosis and improved continuous severity labeling as compared with an RSD for plus disease. If implemented in practice, AI-based VSS could reduce interobserver variability and could standardize treatment for infants with ROP. Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Oral epithelial dysplasia with lymphocytic immune response: clinicopathological characterisation of 44 cases.

Oral epithelial dysplasia (OED) often exhibits a lymphocytic/lichenoid immune response (LIR), imparting histological resemblance to lichenoid mucositis and rendering diagnosis challenging. The clinical appearances of OED and lichenoid inflammatory processes are generally divergent, presenting as well-demarcated hyperkeratotic plaques and diffuse white and/or red mucosal change with variably prominent Wickham striae, respectively. To date, clinicopathological characterisation of OED with LIR, including clinical/gross appearance, has not been depicted. Cases of solitary OED with LIR for which a clinical photograph was available were identified in the authors' institutional files. Clinical and histological features were documented. In 44 identified cases, dysplasia was mild (19 of 44, 43.2%), moderate (19 of 44, 43.2%) and severe (six of 44, 13.6%). Clinically/grossly, all 44 cases (100.0%), presented as well-demarcated hyperkeratotic plaques lacking diffuse white-and-red mucosal change or Wickham striae. Histologically, OED with LIR exhibited numerous 'lichenoid' features beyond the lymphocytic band in the superficial lamina propria, including: leucocyte transmigration (38 of 44, 86.4%), spongiosis (37 of 44, 84.1%), Civatte/colloid bodies (36 of 44, 81.8%), basal cell degeneration (29 of 45, 65.9%), sawtooth rete ridges (11 of 44, 25.0%) and subepithelial clefting (7 of 44, 15.9%). Virtually any lichenoid histological feature may be seen in OED with LIR, representing a significant diagnostic pitfall. The typical clinical appearance of OED with LIR is of a well-demarcated hyperkeratotic plaque, characteristic of keratinising dysplasia and devoid of lichenoid features. This suggests that pathologist access to clinical photographs during diagnostic interpretation of biopsied white lesions, which represents opportunity to perform gross examination of the disease process, may reduce interobserver variability and improve diagnostic accuracy in this challenging differential diagnosis.

Digital Microscopy Augmented by Artificial Intelligence to Interpret Bone Marrow Samples for Hematological Diseases.

Analysis of bone marrow aspirates (BMAs) is an essential step in the diagnosis of hematological disorders. This analysis is usually performed based on a visual examination of samples under a conventional optical microscope, which involves a labor-intensive process, limited by clinical experience and subject to high observer variability. In this work, we present a comprehensive digital microscopy system that enables BMA analysis for cell type counting and differentiation in an efficient and objective manner. This system not only provides an accessible and simple method to digitize, store, and analyze BMA samples remotely but is also supported by an Artificial Intelligence (AI) pipeline that accelerates the differential cell counting process and reduces interobserver variability. It has been designed to integrate AI algorithms with the daily clinical routine and can be used in any regular hospital workflow.

Validation of a deep-learning segmentation model for adult and pediatric head and neck radiotherapy in different patient positions

Background and purposeAutocontouring for radiotherapy has the potential to significantly save time and reduce interobserver variability. We aimed to assess the performance of a commercial autocontouring model for head and neck (H&N) patients in eight orientations relevant to particle therapy with fixed beam lines, focusing on validation and implementation for routine clinical use. Materials and methodsAutocontouring was performed on sixteen organs at risk (OARs) for 98 adult and pediatric patients with 137 H&N CT scans in eight orientations. A geometric comparison of the autocontours and manual segmentations was performed using the Hausdorff Distance 95th percentile, Dice Similarity Coefficient (DSC) and surface DSC and compared to interobserver variability where available. Additional qualitative scoring and dose-volume-histogram (DVH) parameters analyses were performed for twenty patients in two positions, consisting of scoring on a 0–3 scale based on clinical usability and comparing the mean (Dmean) and near-maximum (D2%) dose, respectively. ResultsFor the geometric analysis, the model performance in head-first-supine straight and hyperextended orientations was in the same range as the interobserver variability. HD95, DSC and surface DSC was heterogeneous in other orientations. No significant geometric differences were found between pediatric and adult autocontours. The qualitative scoring yielded a median score of ≥ 2 for 13/16 OARs while 7/32 DVH parameters were significantly different. ConclusionsFor head-first-supine straight and hyperextended scans, we found that 13/16 OAR autocontours were suited for use in daily clinical practice and subsequently implemented. Further development is needed for other patient orientations before implementation.

Artificial intelligence assisted endoscopic ultrasound for detection of pancreatic space-occupying lesion: a systematic review and meta-analysis.

Diagnosing pancreatic lesions, including chronic pancreatitis, autoimmune pancreatitis, and pancreatic cancer, poses a challenge and, as a result, is time-consuming. To tackle this issue, artificial intelligence (AI) has been increasingly utilized over the years. AI can analyze large data sets with heightened accuracy, reduce interobserver variability, and can standardize the interpretation of radiologic and histopathologic lesions. Therefore, this study aims to review the use of AI in the detection and differentiation of pancreatic space-occupying lesions and to compare AI-assisted endoscopic ultrasound (EUS) with conventional EUS in terms of their detection capabilities. Literature searches were conducted through PubMed/Medline, SCOPUS, and Embase to identify studies eligible for inclusion. Original articles, including observational studies, randomized control trials, systematic reviews, meta-analyses, and case series specifically focused on AI-assisted EUS in adults, were included. Data were extracted and pooled, and a meta-analysis was conducted using Meta-xl. For results exhibiting significant heterogeneity, a random-effects model was employed; otherwise, a fixed-effects model was utilized. A total of 21 studies were included in the review with four studies pooled for a meta-analysis. A pooled accuracy of 93.6% (CI 90.4-96.8%) was found using the random-effects model on four studies that showed significant heterogeneity ( P <0.05) in the Cochrane's Q test. Further, a pooled sensitivity of 93.9% (CI 92.4-95.3%) was found using a fixed-effects model on seven studies that showed no significant heterogeneity in the Cochrane's Q test. When it came to pooled specificity, a fixed-effects model was utilized in six studies that showed no significant heterogeneity in the Cochrane's Q test and determined as 93.1% (CI 90.7-95.4%). The pooled positive predictive value which was done using the random-effects model on six studies that showed significant heterogeneity was 91.6% (CI 87.3-95.8%). The pooled negative predictive value which was done using the random-effects model on six studies that showed significant heterogeneity was 93.6% (CI 90.4-96.8%). AI-assisted EUS shows a high degree of accuracy in the detection and differentiation of pancreatic space-occupying lesions over conventional EUS. Its application may promote prompt and accurate diagnosis of pancreatic pathologies.

Interobserver Agreement in Automatic Segmentation Annotation of Prostate Magnetic Resonance Imaging.

We aimed to compare the performance and interobserver agreement of radiologists manually segmenting images or those assisted by automatic segmentation. We further aimed to reduce interobserver variability and improve the consistency of radiomics features. This retrospective study included 327 patients diagnosed with prostate cancer from September 2016 to June 2018; images from 228 patients were used for automatic segmentation construction, and images from the remaining 99 were used for testing. First, four radiologists with varying experience levels retrospectively segmented 99 axial prostate images manually using T2-weighted fat-suppressed magnetic resonance imaging. Automatic segmentation was performed after 2 weeks. The Pyradiomics software package v3.1.0 was used to extract the texture features. The Dice coefficient and intraclass correlation coefficient (ICC) were used to evaluate segmentation performance and the interobserver consistency of prostate radiomics. The Wilcoxon rank sum test was used to compare the paired samples, with the significance level set at p < 0.05. The Dice coefficient was used to accurately measure the spatial overlap of manually delineated images. In all the 99 prostate segmentation result columns, the manual and automatic segmentation results of the senior group were significantly better than those of the junior group (p < 0.05). Automatic segmentation was more consistent than manual segmentation (p < 0.05), and the average ICC reached >0.85. The automatic segmentation annotation performance of junior radiologists was similar to that of senior radiologists performing manual segmentation. The ICC of radiomics features increased to excellent consistency (0.925 [0.888~0.950]). Automatic segmentation annotation provided better results than manual segmentation by radiologists. Our findings indicate that automatic segmentation annotation helps reduce variability in the perception and interpretation between radiologists with different experience levels and ensures the stability of radiomics features.

Patterns of failure for recurrent head and neck squamous cell carcinoma treated with salvage surgery and postoperative IMRT reirradiation

Purpose/ObjectivesThe purpose of this study was to evaluate patterns of locoregional recurrence (LRR) after surgical salvage and adjuvant reirradiation with IMRT for recurrent head and neck squamous cell cancer (HNSCC). Materials/MethodsPatterns of LRR for 61 patients treated consecutively between 2003 and 2014 who received post-operative IMRT reirradiation to ≥ 60 Gy for recurrent HNSCC were determined by 2 methods: 1) physician classification via visual comparison of post-radiotherapy imaging to reirradiation plans; and 2) using deformable image registration (DIR). Those without evaluable CT planning image data were excluded. All recurrences were verified by biopsy or radiological progression. Failures were defined as in-field, marginal, or out-of-field. Logistic regression analyses were performed to identify predictors for LRR. ResultsA total of 55 patients were eligible for analysis and 23 (42 %) had documented LRR after reirradiation. Location of recurrent disease prior to salvage surgery (lymphatic vs. mucosal) was the most significant predictor of LRR after post-operative reirradiation with salvage rate of 67 % for lymphatic vs. 33 % for mucosal sites (p = 0.037). Physician classification of LRR yielded 14 (61 %) in-field failures, 3 (13 %) marginal failures, and 6 (26 %) out-of-field failures, while DIR yielded 10 (44 %) in-field failures, 4 (17 %) marginal failures, and 9 (39 %) out-of-field failures. Most failures (57 %) occurred within the original site of recurrence or first echelon lymphatic drainage. Of patients who had a free flap placed during salvage surgery, 56 % of failures occurred within 1 cm of the surgical flap. ConclusionOur study highlights the role of DIR in enhancing the accuracy and consistency of POF analysis. Compared to traditional visual inspection, DIR reduces interobserver variability and provides more nuanced insights into dose-specific and spatial parameters of locoregional recurrences. Additionally, the study identifies the location of the initial recurrence as a key predictor of subsequent locoregional recurrence after salvage surgery and re-IMRT.

HER2 in situ hybridization testing in breast cancer: Applying algorithm-assisted assessment to reduce interobserver variability in difficult cases.

e13561 Background: Accurate assessment of HER2 expression by HER2 immunohistochemistry and in-situ hybridization (ISH) is critical for the management of patients with breast cancer. The revised 2018 ASCO/CAP guidelines defined 5 subgroups based on HER2 expression and copy number. Few reports have investigated interobserver variability when applying the revised guidelines. Digital algorithms may have a role in assisting pathologists in assessing cases with equivocal and uncommon patterns of HER2 amplification. This study was designed to evaluate interobserver variability in the gold standard manual assessment of HER2 ISH, particularly in less common HER2 ISH groups. Subsequently, we evaluated whether a new digital image analysis algorithm (Roche uPath HER2 Dual ISH image analysis) could reduce interobserver variability and potentially improve patient selection for targeted anti-HER2 therapy. Methods: Of 2982 breast cancer cases, we derived an enriched cohort of 99 patient cases with HER2 IHC 2+ or 3+ and selective ISH results (groups 2-4, evidence of HER2 heterogeneity, borderline negative group 5 and borderline positive group 1). As per guidelines, a minimum of 20 tumour cells per slide were manually and independently counted by 4 anatomical pathologists. After a washout period and second round of de-identification, the slides were scanned (DP200; Roche) and re-scored using the digital algorithm. Results: Pathologist reporting of patient HER2 status (HER2 positive vs. HER2 negative) using manual microscopy demonstrated significant interobserver variability, with a Fleiss’s kappa value of 0.471 (95% CI: 0.378-0.564; P= 1.24E-21) indicating fair-moderate agreement. Interobserver variability in manual scoring of HER2 ISH at the level of HER2 group designation (groups 1-5) showed poor-moderate reliability between pathologists, with an intraclass correlation coefficient (ICC) of 0.526 (95% CI: 0.407-0.641; P= 9.28E-21). Repeat analysis of the cohort using algorithm-assisted quantification resulted in moderate-substantial concordance in HER2 patient status reporting, with a Fleiss’s kappa value of 0.666 (95% CI: 0.572-0.759; P= 1.70E-40). Algorithm-assisted quantification resulted in moderate-good agreement of HER2 group designation, with an ICC of 0.763 (95% CI: 0.683-0.832; P= 8.76E-48). In sub-group analysis, use of the algorithm improved concordance particularly in groups 2,4 and 5. Time to report cases was also significantly reduced with the use of the algorithm. Conclusions: Our study demonstrates the potential to improve the concordance of HER2 amplification status reporting in less common HER2 subgroups using a digital algorithm and potentially improve therapy selection and outcomes for patients with HER2-low and borderline HER2-amplified breast cancers.

Fully Automated Tumor Bud Assessment in Hematoxylin and Eosin-Stained Whole Slide Images of Colorectal Cancer

Tumor budding (TB), the presence of single cells or small clusters of up to 4 tumor cells at the invasive front of colorectal cancer (CRC), is a proven risk factor for adverse outcomes. International definitions are necessary to reduce interobserver variability. According to the current international guidelines, hotspots at the invasive front should be counted in hematoxylin and eosin (H&E)-stained slides. This is time-consuming and prone to interobserver variability; therefore, there is a need for computer-aided diagnosis solutions. In this study, we report an artificial intelligence-based method for detecting TB in H&E-stained whole slide images. We propose a fully automated pipeline to identify the tumor border, detect tumor buds, characterize them based on the number of tumor cells, and produce a TB density map to identify the TB hotspot. The method outputs the TB count in the hotspot as a computational biomarker. We show that the proposed automated TB detection workflow performs on par with a panel of 5 pathologists at detecting tumor buds and that the hotspot-based TB count is an independent prognosticator in both the univariate and the multivariate analysis, validated on a cohort of n = 981 patients with CRC. Computer-aided detection of tumor buds based on deep learning can perform on par with expert pathologists for the detection and quantification of tumor buds in H&E-stained CRC histopathology slides, strongly facilitating the introduction of budding as an independent prognosticator in clinical routine and clinical trials.

Computer assisted interpretation of Tc-99m mercaptoacetyltriglycine diuretic scintigraphy enhances resident performance.

iRENEX is a software module that incorporates scintigraphic and clinical data to interpret 99m Tc- mercaptoacetyltriglycine (MAG3) diuretic studies and provide reasons for their conclusions. Our objectives were to compare iRENEX interpretations with those of expert physicians, use iRENEX to evaluate resident performance and determine if iRENEX could improve the diagnostic accuracy of experienced residents. Baseline and furosemide 99m Tc-MAG3 acquisitions of 50 patients with suspected obstruction (mean age ± SD, 58.7 ± 15.8 years, 60% female) were randomly selected from an archived database and independently interpreted by iRENEX, three expert readers and four nuclear medicine residents with one full year of residency. All raters had access to scintigraphic data and a text file containing clinical information and scored each kidney on a scale from +1.0 to -1.0. Scores ≥0.20 represented obstruction with higher scores indicating greater confidence. Scores +0.19 to -0.19 were indeterminate; scores ≤-0.20 indicated no obstruction. Several months later, residents reinterpreted the studies with access to iRENEX. Receiver operating characteristic (ROC) analysis and concordance correlation coefficient (CCC) quantified agreement. The CCC among experts was higher than that among residents, 0.84, versus 0.39, respectively, P < 0.001. When residents reinterpreted the studies with iRENEX, their CCC improved from 0.39 to 0.73, P < 0.001. ROC analysis showed significant improvement in the ability of residents to distinguish between obstructed and non-obstructed kidneys using iRENEX ( P = 0.036). iRENEX interpretations were comparable to those of experts. iRENEX reduced interobserver variability among experienced residents and led to better agreement between resident and expert interpretations.

Traversing Their Path to the Peripheral Smear: The Journey of Traumatized Red Blood Cells.

Background Thrombotic microangiopathy encompasses a wide range of conditions, of which thrombotic thrombocytopenic purpura being a medical emergency requires prompt intervention, with schistocytes being a reliable morphological indicator of microvascular injury. However, there are conditions other than thrombotic microangiopathic anemia where schistocytes can be seen in large numbers. These nonthrombotic microangiopathic conditions are broadly grouped under cytoskeletal abnormalities, mechanical damage, and thermal injuries. Automated methods in schistocyte evaluation have shown varied reproducibility requiring manual identification. International Council for Standardization in Hematology (ICSH) recommends standardized morphological criteria and quantitative assessment as a percentage after counting at least 1,000 red blood cells in optimal areas of smear to reduce interobserver variability. Objectives The aim of this study was to evaluate and quantitate schistocytes in thrombotic microangiopathic and nonthrombotic microangiopathic groups using ICSH guidelines and to evaluate interobserver reproducibility of manual schistocyte count. Materials and Methods Overall, 157 peripheral blood smears showing schistocytes were studied by two independent observers using ICSH recommendations on light microscopy. The hematological findings were correlated with clinical diagnosis and other relevant investigations. Results Schistocytes were observed in five cases of thrombotic microangiopathic anemia and 152 cases of nonthrombotic microangiopathic anemia. Schistocyte count in thrombotic microangiopathic anemia and nonthrombotic microangiopathic anemia groups with mean (±standard deviation) value was 2.28 ± 2.65% and 0.76 ± 0.67%, respectively ( p < 0.001). The correlation coefficient between the two observers was 0.59 (confidence interval = 0.966-1.346) showing an excellent agreement on the reproducibility of schistocytes by application of ICSH guidelines. Conclusion Percentage of schistocytes more than 1% is a robust morphological indicator for diagnosis of thrombotic microangiopathic anemia in adults. Strict application of ICSH guidelines reduces interobserver bias.

The Role of Artificial Intelligence in Echocardiography.

Echocardiography is an integral part of the diagnosis and management of cardiovascular disease. The use and application of artificial intelligence (AI) is a rapidly expanding field in medicine to improve consistency and reduce interobserver variability. AI can be successfully applied to echocardiography in addressing variance during image acquisition and interpretation. Furthermore, AI and machine learning can aid in the diagnosis and management of cardiovascular disease. In the realm of echocardiography, accurate interpretation is largely dependent on the subjective knowledge of the operator. Echocardiography is burdened by the high dependence on the level of experience of the operator, to a greater extent than other imaging modalities like computed tomography, nuclear imaging, and magnetic resonance imaging. AI technologies offer new opportunities for echocardiography to produce accurate, automated, and more consistent interpretations. This review discusses machine learning as a subfield within AI in relation to image interpretation and how machine learning can improve the diagnostic performance of echocardiography. This review also explores the published literature outlining the value of AI and its potential to improve patient care.

A planning-based feasibility study of MR-Linac treatment for anal cancer radiation therapy.

The hybrid magnetic resonance image (MRI) scanner and radiation therapy linear accelerator (MR-Linac) has the potential to enhance clinical outcomes for anal cancer (AC) patients with improved soft tissue visualization and daily plan adaption but has planning and delivery limitations due to the incorporation of MRI. We aimed to identify if Elekta Unity MR-Linac-based radiation therapy is feasible for anal cancer. Ten prospectively enrolled AC patients treated with radical chemoradiotherapy were replanned for MR-Linac treatment using departmental planning criteria. For comparison, and to reduce interobserver variability, volumetric modulated arc radiation therapy (VMAT) plans were also created for each patient by the same single senior radiation therapist. Plans were compared using departmental dosimetric plan criteria, as well as conformity and homogeneity indices, monitor units (MUs) and measured plan delivery (beam-on) time. Results were deemed clinically acceptable. Target and organ at risk (OAR) doses were comparable between MR-Linac plans and VMAT plans, although PTV45Gy D98% coverage was compromised in 3 of 10 MR-Linac plans due to caudocranial length exceeding the limits of the MR-Linac. MR-Linac plans had lower MUs, median of 689.1 vs 849.65 (p = 0.002), but took over twice as long to deliver, 529.5s vs 224s (p = <0.0001) as VMAT plans. MR-Linac planning and treatment of AC is feasible for a subset of patients. The current physical limitations of the Elekta Unity system mean patients with large caudocranial elective PTV45Gy target volumes may not be covered dosimetrically to the required clinical standard. Longer image verification and treatment delivery times of the MR-Linac also mean patient selection and intrafractional IGRT are likely to be integral to ensuring high quality clinical outcomes in this rare cancer.

Reduction of inter-observer variability using MRI and CT fusion in delineating of primary tumor for radiotherapy in lung cancer with atelectasis

PurposeTo compare the difference between magnetic resonance imaging (MRI) and computed tomography (CT) in delineating the target area of lung cancer with atelectasis.MethodA retrospective analysis was performed on 15 patients with lung cancer accompanied by atelectasis. All positioning images were transferred to Eclipse treatment planning systems (TPSs). Six MRI sequences (T1WI, T1WI+C, T1WI+C Delay, T1WI+C 10 minutes, T2WI, DWI) were registered with positioning CT. Five radiation oncologists delineated the tumor boundary to obtain the gross tumor volume (GTV). Conformity index (CI) and dice coefficient (DC) were used to measure differences among observers.ResultsThe differences in delineation mean volumes, CI, and DC among CT and MRIs were significant. Multiple comparisons were made between MRI sequences and CT. Among them, DWI, T2WI, and T1WI+C 10 minutes sequences were statistically significant with CT in mean volumes, DC, and CI. The mean volume of DWI, T2WI, and T1WI+C 10 minutes sequence in the target area is significantly smaller than that on the CT sequence, but the consistency is higher than that of CT sequences.ConclusionsThe recognition of atelectasis by MRI was better than that by CT, which could reduce interobserver variability of primary tumor delineation in lung cancer with atelectasis. Among them, DWI, T2WI, T1WI+C 10 minutes may be a better choice to improve the GTV delineation of lung cancer patients with atelectasis.

Tracked 3D ultrasound and deep neural network-based thyroid segmentation reduce interobserver variability in thyroid volumetry.

Thyroid volumetry is crucial in the diagnosis, treatment, and monitoring of thyroid diseases. However, conventional thyroid volumetry with 2D ultrasound is highly operator-dependent. This study compares 2D and tracked 3D ultrasound with an automatic thyroid segmentation based on a deep neural network regarding inter- and intraobserver variability, time, and accuracy. Volume reference was MRI. 28 healthy volunteers (24—50 a) were scanned with 2D and 3D ultrasound (and by MRI) by three physicians (MD 1, 2, 3) with different experience levels (6, 4, and 1 a). In the 2D scans, the thyroid lobe volumes were calculated with the ellipsoid formula. A convolutional deep neural network (CNN) automatically segmented the 3D thyroid lobes. 26, 6, and 6 random lobe scans were used for training, validation, and testing, respectively. On MRI (T1 VIBE sequence) the thyroid was manually segmented by an experienced MD. MRI thyroid volumes ranged from 2.8 to 16.7ml (mean 7.4, SD 3.05). The CNN was trained to obtain an average Dice score of 0.94. The interobserver variability comparing two MDs showed mean differences for 2D and 3D respectively of 0.58 to 0.52ml (MD1 vs. 2), −1.33 to −0.17ml (MD1 vs. 3) and −1.89 to −0.70ml (MD2 vs. 3). Paired samples t-tests showed significant differences for 2D (p = .140, p = .002 and p = .002) and none for 3D (p = .176, p = .722 and p = .057). Intraobsever variability was similar for 2D and 3D ultrasound. Comparison of ultrasound volumes and MRI volumes showed a significant difference for the 2D volumetry of all MDs (p = .002, p = .009, p <.001), and no significant difference for 3D ultrasound (p = .292, p = .686, p = 0.091). Acquisition time was significantly shorter for 3D ultrasound. Tracked 3D ultrasound combined with a CNN segmentation significantly reduces interobserver variability in thyroid volumetry and increases the accuracy of the measurements with shorter acquisition times.

Deep learning-enabled assessment of cardiac allograft rejection from endomyocardial biopsies.

Endomyocardial biopsy (EMB) screening represents the standard of care for detecting allograft rejections after heart transplant. Manual interpretation of EMBs is affected by substantial interobserver and intraobserver variability, which often leads to inappropriate treatment with immunosuppressive drugs, unnecessary follow-up biopsies and poor transplant outcomes. Here we present a deep learning-based artificial intelligence (AI) system for automated assessment of gigapixel whole-slide images obtained from EMBs, which simultaneously addresses detection, subtyping and grading of allograft rejection. To assess model performance, we curated a large dataset from the United States, as well as independent test cohorts from Turkey and Switzerland, which includes large-scale variability across populations, sample preparations and slide scanning instrumentation. The model detects allograft rejection with an area under the receiver operating characteristic curve (AUC) of 0.962; assesses the cellular and antibody-mediated rejection type with AUCs of 0.958 and 0.874, respectively; detects Quilty B lesions, benign mimics of rejection, with an AUC of 0.939; and differentiates between low-grade and high-grade rejections with an AUC of 0.833. In a human reader study, the AI system showed non-inferior performance to conventional assessment and reduced interobserver variability and assessment time. This robust evaluation of cardiac allograft rejection paves the way for clinical trials to establish the efficacy of AI-assisted EMB assessment and its potential for improving heart transplant outcomes.

Deep learning for diagnosis of precancerous lesions in upper gastrointestinal endoscopy: A review.

Upper gastrointestinal (GI) cancers are the leading cause of cancer-related deaths worldwide. Early identification of precancerous lesions has been shown to minimize the incidence of GI cancers and substantiate the vital role of screening endoscopy. However, unlike GI cancers, precancerous lesions in the upper GI tract can be subtle and difficult to detect. Artificial intelligence techniques, especially deep learning algorithms with convolutional neural networks, might help endoscopists identify the precancerous lesions and reduce interobserver variability. In this review, a systematic literature search was undertaken of the Web of Science, PubMed, Cochrane Library and Embase, with an emphasis on the deep learning-based diagnosis of precancerous lesions in the upper GI tract. The status of deep learning algorithms in upper GI precancerous lesions has been systematically summarized. The challenges and recommendations targeting this field are comprehensively analyzed for future research.